# Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation

arXiv: https://arxiv.org/abs/2307.02808 · HTML: https://mlsanity.com/paper/2307.02808/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 70 references that are in the map.
- First posted on arXiv 6 Jul 2023.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Open3D: A Modern Library for 3D Data Processing](https://mlsanity.com/paper/1801.09847/) (2018)
- [Blind Image Quality Assessment Using A Deep Bilinear Convolutional Neural Network](https://mlsanity.com/paper/1907.02665/) (2019)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Patch-VQ: 'Patching Up' the Video Quality Problem](https://mlsanity.com/paper/2011.13544/) (2020)
- [AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2306.04717/) (2023)
- [Blind Quality Assessment for in-the-Wild Images via Hierarchical Feature Fusion and Iterative Mixed Database Training](https://mlsanity.com/paper/2105.14550/) (2021)
- [Inferring Point Cloud Quality via Graph Similarity](https://mlsanity.com/paper/2006.00497/) (2020)
- [A Perceptual Quality Assessment Exploration for AIGC Images](https://mlsanity.com/paper/2303.12618/) (2023)
- [Point Cloud Quality Assessment: Dataset Construction and Learning-based No-Reference Metric](https://mlsanity.com/paper/2012.11895/) (2020)
- [No-Reference Quality Assessment for 3D Colored Point Cloud and Mesh Models](https://mlsanity.com/paper/2107.02041/) (2021)
- [Perceptual Quality Assessment of Colored 3D Point Clouds](https://mlsanity.com/paper/2111.05474/) (2021)
- [MM-PCQA: Multi-Modal Learning for No-reference Point Cloud Quality Assessment](https://mlsanity.com/paper/2209.00244/) (2022)
- [Textured Mesh Quality Assessment: Large-Scale Dataset and Deep Learning-based Quality Metric](https://mlsanity.com/paper/2202.02397/) (2022)
- [A No-reference Quality Assessment Metric for Point Cloud Based on Captured Video Sequences](https://mlsanity.com/paper/2206.05054/) (2022)
- [Evaluating Point Cloud from Moving Camera Videos: A No-Reference Metric](https://mlsanity.com/paper/2208.14085/) (2022)
- [VDPVE: VQA Dataset for Perceptual Video Enhancement](https://mlsanity.com/paper/2303.09290/) (2023)
- [BASICS: Broad quality Assessment of Static point clouds In Compression Scenarios](https://mlsanity.com/paper/2302.04796/) (2023)
- [Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessment](https://mlsanity.com/paper/2304.14672/) (2023)
- [Perceptual Quality Assessment for Digital Human Heads](https://mlsanity.com/paper/2209.09489/) (2022)
- [Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancement](https://mlsanity.com/paper/2305.09512/) (2023)
- [Blind Quality Assessment of 3D Dense Point Clouds with Structure Guided Resampling](https://mlsanity.com/paper/2208.14603/) (2022)

## Built on by (most cited first, 27 of 27)

- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving](https://mlsanity.com/paper/2405.20337/) (2024)
- [Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment](https://mlsanity.com/paper/2403.11956/) (2024)
- [AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2404.03407/) (2024)
- [MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model](https://mlsanity.com/paper/2402.16749/) (2024)
- [Quality Assessment in the Era of Large Models: A Survey](https://mlsanity.com/paper/2409.00031/) (2024)
- [Q-Refine: A Perceptual Quality Refiner for AI-Generated Image](https://mlsanity.com/paper/2401.01117/) (2024)
- [NTIRE 2024 Quality Assessment of AI-Generated Content Challenge](https://mlsanity.com/paper/2404.16687/) (2024)
- [StableVQA: A Deep No-Reference Quality Assessment Model for Video Stability](https://mlsanity.com/paper/2308.04904/) (2023)
- [MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis](https://mlsanity.com/paper/2411.11235/) (2024)
- [Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2404.15163/) (2024)
- [THQA: A Perceptual Quality Assessment Database for Talking Heads](https://mlsanity.com/paper/2404.09003/) (2024)
- [G-Refine: A General Quality Refiner for Text-to-Image Generation](https://mlsanity.com/paper/2404.18343/) (2024)
- [Dual-Branch Network for Portrait Image Quality Assessment](https://mlsanity.com/paper/2405.08555/) (2024)
- [Light-VQA+: A Video Quality Assessment Model for Exposure Correction with Vision-Language Guidance](https://mlsanity.com/paper/2405.03333/) (2024)
- [CMC-Bench: Towards a New Paradigm of Visual Signal Compression](https://mlsanity.com/paper/2406.09356/) (2024)
- [3DGCQA: A Quality Assessment Database for 3D AI-Generated Contents](https://mlsanity.com/paper/2409.07236/) (2024)
- [NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results](https://mlsanity.com/paper/2506.02875/) (2025)
- [Simple Baselines for Projection-based Full-reference and No-reference Point Cloud Quality Assessment](https://mlsanity.com/paper/2310.17147/) (2023)
- [GeodesicPSIM: Predicting the Quality of Static Mesh with Texture Map via Geodesic Patch Similarity](https://mlsanity.com/paper/2308.04928/) (2023)
- [How Social is It? A Benchmark for LLMs' Capabilities in Multi-user Multi-turn Social Agent Tasks](https://mlsanity.com/paper/2505.04628/) (2025)
- [EvalTalker: Learning to Evaluate Real-Portrait-Driven Multi-Subject Talking Humans](https://mlsanity.com/paper/2512.01340/) (2025)
- [Efficient Face Image Quality Assessment via Self-training and Knowledge Distillation](https://mlsanity.com/paper/2507.15709/) (2025)
- [DHQA-4D: Perceptual Quality Assessment of Dynamic 4D Digital Human](https://mlsanity.com/paper/2510.03874/) (2025)
- [Who is a Better Talker: Subjective and Objective Quality Assessment for AI-Generated Talking Heads](https://mlsanity.com/paper/2507.23343/) (2025)
- [Score2Instruct: Scaling Up Video Quality-Centric Instructions via Automated Dimension Scoring](https://mlsanity.com/paper/2506.21011/) (2025)

## Abstract (arXiv)

Digital humans have witnessed extensive applications in various domains, necessitating related quality assessment studies. However, there is a lack of comprehensive digital human quality assessment (DHQA) databases. To address this gap, we propose SJTU-H3D, a subjective quality assessment database specifically designed for full-body digital humans. It comprises 40 high-quality reference digital humans and 1,120 labeled distorted counterparts generated with seven types of distortions. The SJTU-H3D database can serve as a benchmark for DHQA research, allowing evaluation and refinement of processing algorithms. Further, we propose a zero-shot DHQA approach that focuses on no-reference (NR) scenarios to ensure generalization capabilities while mitigating database bias. Our method leverages semantic and distortion features extracted from projections, as well as geometry features derived from the mesh structure of digital humans. Specifically, we employ the Contrastive Language-Image Pre-training (CLIP) model to measure semantic affinity and incorporate the Naturalness Image Quality Evaluator (NIQE) model to capture low-level distortion information. Additionally, we utilize dihedral angles as geometry descriptors to extract mesh features. By aggregating these measures, we introduce the Digital Human Quality Index (DHQI), which demonstrates significant improvements in zero-shot performance. The DHQI can also serve as a robust baseline for DHQA tasks, facilitating advancements in the field. The database and the code are available at https://github.com/zzc-1998/SJTU-H3D.